Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6016 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0001

Data Index: 846216 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0001

Data Index: 388041 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0001

Data Index: 380438 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0001

Data Index: 161975 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1131214 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0001

Data Index: 74096 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0001

Data Index: 855089 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0130. Min Act: -0.0001

Data Index: 1104156 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0001

Data Index: 228763 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1020000 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0001

Data Index: 181261 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0001

Data Index: 623944 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0001

Data Index: 825934 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0001

Data Index: 299883 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1302088 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0001

Data Index: 444861 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0001

Data Index: 431844 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1025817 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1018128 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1075071 (C4 (Web Text))

Max Activating Token Index: 674